Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

shenzhi-wang
/
Llama3.1-8B-Chinese-Chat

Text Generation
Transformers
Safetensors
GGUF
English
Chinese
llama
llama-factory
orpo
conversational
text-generation-inference
Model card Files Files and versions
xet
Community
22
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

[AUTOMATED] Model Memory Requirements

#22 opened 7 months ago by
Fuji1995

What should be the correct version of "torch" and "transformers"?

#21 opened 9 months ago by
TKLTao

Add if add_generation_prompt to the chat template

#20 opened 10 months ago by
Galaxy-Husky

拒答非常严重

1
#18 opened 12 months ago by
zhichen

【咨询】请问一下大佬,微调一个8b模型的费用是多少啊?

#17 opened about 1 year ago by
taurusduan

does not support tools

2
#16 opened about 1 year ago by
shenjianxin

GPT4All最新版加载llama3.1_8b_chinese_chat_q4_k_m.gguf 后python代码报错

#14 opened about 1 year ago by
jumpfox

Error: json: cannot unmarshal array into Go struct field Params.eos_token_id of type int

1
#10 opened about 1 year ago by
asdfsadfsdf

感觉效果不如之前orpo的llama3

2
#8 opened about 1 year ago by
ztyl-tech

有没有对比的指标?

2
#7 opened about 1 year ago by
okcwang

Train data?

2
#5 opened about 1 year ago by
yyq90

any compare result with original llama3.1-inst?

#3 opened about 1 year ago by
okcwang

等量化版本

#2 opened about 1 year ago by
lukbinx
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs